Wyniki wyszukiwania - BazTech

Ograniczanie wyników

3 Biocybernetics and Biomedical Engineering

Powiadomienia systemowe

Sesja wygasła!
Sesja wygasła!
Sesja wygasła!
Sesja wygasła!
Sesja wygasła!

Znaleziono wyników: 3

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

Computer-aided diagnosis of clinically significant prostate cancer from MRI images using sparse autoencoder and random forest classifier

Abraham B., Nair M. S.

Biocybernetics and Biomedical Engineering

2018

Vol. 38, no. 3

733--744

A novel method to diagnose clinically significant prostate cancer (PCa) using Multi-parametric Magnetic Resonance Imaging (mpMRI) biomarkers in a highly imbalanced dataset is investigated in this paper. Transaxial T2 Weighted (T2W), Apparent Diffusion Coefficient (ADC) and high B-Value (BVAL) Diffusion-Weighted (DW) images obtained from PROSTATEx 2016 challenge dataset publicly available in TCIA (The Cancer Imaging Archive) is used for this study. High-level features are extracted using a single layer Sparse Autoencoder (SAE). Synthetic Minority Oversampling Technique (SMOTE), Weka Resample algorithm and Adaptive Synthetic (ADASYN) sampling approach are explored to solve the class-imbalance problem. The performance of various classifiers are also investigated and it was found that the data augmented using ADASYN followed by classification using random forest classifier achieved the best performance. It achieved an area under ROC curve of 0.979. It also reached a Cohen's kappa score of 0.873, an accuracy of 93.65% and F-Measure of 0.94 in distinguishing clinically significant PCa from indolent Pca.

Automatic segmentation of cell nuclei using Krill Herd optimization based multi-thresholding and Localized Active Contour Model

Beevi K. S., Nair M. S., Bindu G. R.

Biocybernetics and Biomedical Engineering

2016

Vol. 36, no. 4

584--596

Analysis of tissue components in histopathology image stays on as the gold standard in detecting different types of cancers. Active Contour Models (ACM) serve as a widely useful tool in object segmentation in pathology images. Since the ACMs are susceptible to initial contour placement, efficiency of object detection is very much influenced by the selection of primary curve placement technique. In this paper, in order to handle diffused intensities present along object boundaries in histopathology images, segmentation of nuclei from breast histopathology images are carried out by Localized Active Contour Model (LACM) utilizing bio-inspired optimization techniques in the detection stage. Krill Herd Algorithm (KHA) based optimal curve placement provides better initial boundaries compared with other detection techniques. The segmentation performance is investigated based on Housdorff (HD) and Maximum Absolute Distance (MAD) measures. The algorithm also shows comparable performance with other state-of-the-art techniques in terms of quantitative measures such as Precision, Accuracy and Touching Nuclei Resolution when applied to complex images of stained breast biopsy slides.

A novel approach for detection and delineation of cell nuclei using feature similarity index measure

John J., Nair M. S., Kumar P. R. A., Wilscy M.

Biocybernetics and Biomedical Engineering

2016

Vol. 36, no. 1

76--88

Accurate image segmentation of cells and tissues is a challenging research area due to its vast applications in medical diagnosis. Seed detection is the basic and most essential step for the automated segmentation of microscopic images. This paper presents a robust, accurate and novel method for detecting cell nuclei which can be efficiently used for cell segmentation. We propose a template matching method using a feature similarity index measure (FSIM) for detecting nuclei positions in the image which can be further used as seeds for segmentation tasks. Initially, a Fuzzy C-Means clustering algorithm is applied on the image for separating the foreground region containing the individual and clustered nuclei regions. FSIM based template matching approach is then used for nuclei detection. FSIM makes use of low level texture features for comparisons and hence gives good results. The performance of the proposed method is evaluated on the gold standard dataset containing 36 images (_8000 nuclei) of tissue samples and also in vitro cultured cell images of Stromal Fibroblasts (5 images) and Human Macrophage cell line (4 images) using the statistical measures of Precision and Recall. The results are analyzed and compared with other state-of-the-art methods in the literature and software tools to prove its efficiency. Precision is found to be comparable and the Recall rate is found to exceed 92% for the gold standard dataset which shows considerable performance improvement over existing methods.